Settling the sample complexity of model-based offline reinforcement learning-Reference-Cited by-同舟云学术

Settling the sample complexity of model-based offline reinforcement learning

Published:2024-02-01 Issue:1 Volume:52 Page:
ISSN:0090-5364
Container-title:The Annals of Statistics
language:
Short-container-title:Ann. Statist.

Author:

Li Gen¹,Shi Laixi²,Chen Yuxin³,Chi Yuejie⁴,Wei Yuting³

Affiliation:

1. Department of Statistics, Chinese University of Hong Kong

2. Department of Computing Mathematical Sciences, California Institute of Technology

3. Department of Statistics and Data Science, The Wharton School, University of Pennsylvania

4. Department of Electrical and Computer Engineering, Carnegie Mellon University

Publisher

Institute of Mathematical Statistics

Reference83 articles.

1. GHESHLAGHI AZAR, M., MUNOS, R. and KAPPEN, H. J. (2013). Minimax PAC bounds on the sample complexity of reinforcement learning with a generative model. Mach. Learn. 91 325–349.

2. LATTIMORE, T. and SZEPESVÁRI, C. (2020). Bandit Algorithms. Cambridge Univ. Press, Cambridge.

3. JIANG, N. and LI, L. (2016). Doubly robust off-policy value evaluation for reinforcement learning. In International Conference on Machine Learning 652–661.

4. LANGE, S., GABEL, T. and RIEDMILLER, M. (2012). Batch reinforcement learning. In Reinforcement Learning 45–73. Springer, Berlin.

5. Robbins, H. and Monro, S. (1951). A stochastic approximation method. Ann. Math. Stat. 22 400–407.

Cited by 4 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. Provably Efficient Offline Reinforcement Learning With Trajectory-Wise Reward;IEEE Transactions on Information Theory;2024-09

2. High-Probability Sample Complexities for Policy Evaluation With Linear Function Approximation;IEEE Transactions on Information Theory;2024-08

3. Model-Based Reinforcement Learning for Offline Zero-Sum Markov Games;Operations Research;2024-04-02

4. Digital Twin-Assisted Edge Service Caching for Consumer Electronics Manufacturing;IEEE Transactions on Consumer Electronics;2024-02